Key takeaways
- Stumpy 1.11.0 introduces the Minkowski Distance and enhances Multi-dimensional Motif Discovery capabilities.
- The library supports various time series analysis tasks, including anomaly detection and pattern discovery.
- Stumpy has gained significant popularity, with over 30,000 downloads and 1,000 GitHub stars.
Sean Law, principal data scientist at Charles Schwab and the creator of Stumpy, announced the release of the latest version 1.11.0. The new version includes the oft-requested Minkowski (p-norm) Distance, support for Multi-dimensional Motif Discovery, new Annotation vector tutorials, and enhancements for Pan Matrix Profiles. The latest version is available on GitHub.
Stumpy is a powerful and scalable library that efficiently computes something called the matrix profile, which can be used for a variety of time series data mining tasks such as:
- pattern/motif (approximately repeated subsequences within a longer time series) discovery
- anomaly/novelty (discord) discovery
- shapelet discovery
- semantic segmentation
- streaming (on-line) data
- fast approximate matrix profiles
- time series chains (temporally ordered set of subsequence patterns)
- snippets for summarising long time series
- pan matrix profiles for selecting the best subsequence window size(s)
With 30K+ downloads, over 1K+ Github stars, and 100% code coverage, Stumpy is a favourite of academics, data scientists, software developers, and time-series enthusiasts.
Check out the latest documentation or explore the hands-on tutorials.
